101 citations · 346 across the 24 of their papers we have counts for
25 papers
Self-Augmented Diffusion Guidance for Physics-Informed Generation
Akira Osaka, Naoya Takeishi, Takehisa Yairi
Diffusion models can be used to generate spatiotemporal signals of physical phenomena, such as time-series images of fluid dynamics. However, a major limitation of standard diffusi…
Forecast Sports Outcomes under Efficient Market Hypothesis: Theoretical and Experimental Analysis of Odds-Only and Generalised Linear Models
Kaito Goto, Naoya Takeishi, Takehisa Yairi
Converting betting odds into accurate outcome probabilities is a fundamental challenge in order to use betting odds as a benchmark for sports forecasting and market efficiency anal…
Learning Visually Interpretable Oscillator Networks for Soft Continuum Robots from Video
Henrik Krauss, Johann Licher, Naoya Takeishi +2
Learning soft continuum robot (SCR) dynamics from video offers flexibility but existing methods lack interpretability or rely on prior assumptions. Model-based approaches require p…
Data-driven simulator of multi-animal behavior with unknown dynamics via offline and online reinforcement learning
Keisuke Fujii, Kazushi Tsutsui, Yu Teshima +6
Simulators of animal movements play a valuable role in studying behavior. Advances in imitation learning for robotics have expanded possibilities for reproducing human and animal m…
A Temporal Difference Method for Stochastic Continuous Dynamics
Haruki Settai, Naoya Takeishi, Takehisa Yairi
For continuous systems modeled by dynamical equations such as ODEs and SDEs, Bellman's Principle of Optimality takes the form of the Hamilton-Jacobi-Bellman (HJB) equation, which p…
Mimicking Better by Matching the Approximate Action Distribution
João A. Cândido Ramos, Lionel Blondé, Naoya Takeishi +1
In this paper, we introduce MAAD, a novel, sample-efficient on-policy algorithm for Imitation Learning from Observations. MAAD utilizes a surrogate reward signal, which can be deri…
Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations
Keisuke Fujii, Kazushi Tsutsui, Atom Scott +3
Modeling of real-world biological multi-agents is a fundamental problem in various scientific and engineering fields. Reinforcement learning (RL) is a powerful framework to generat…
Deep Grey-Box Modeling With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models
Naoya Takeishi, Alexandros Kalousis
The combination of deep neural nets and theory-driven models, which we call deep grey-box modeling, can be inherently interpretable to some extent thanks to the theory backbone. De…
Estimating counterfactual treatment outcomes over time in complex multiagent scenarios
Keisuke Fujii, Koh Takeuchi, Atsushi Kuribayashi +3
Evaluation of intervention in a multiagent system, e.g., when humans should intervene in autonomous driving systems and when a player should pass to teammates for a good shot, is c…
Asteroid Flyby Cycler Trajectory Design Using Deep Neural Networks
Naoya Ozaki, Kanta Yanagida, Takuya Chikazawa +3
Asteroid exploration has been attracting more attention in recent years. Nevertheless, we have just visited tens of asteroids while we have discovered more than one million bodies.…
Learning interaction rules from multi-animal trajectories via augmented behavioral models
Keisuke Fujii, Naoya Takeishi, Kazushi Tsutsui +10
Extracting the interaction rules of biological agents from movement sequences pose challenges in various domains. Granger causality is a practical framework for analyzing the inter…
Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections
Naoya Takeishi, Keisuke Fujii, Koh Takeuchi +1
Extracting coherent patterns is one of the standard approaches towards understanding spatio-temporal data. Dynamic mode decomposition (DMD) is a powerful tool for extracting cohere…
Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling
Naoya Takeishi, Alexandros Kalousis
Integrating physics models within machine learning models holds considerable promise toward learning robust models with improved interpretability and abilities to extrapolate. In t…
Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling
Keisuke Fujii, Naoya Takeishi, Yoshinobu Kawahara +1
Extracting the rules of real-world multi-agent behaviors is a current challenge in various scientific and engineering fields. Biological agents independently have limited observati…
Learning Dynamics Models with Stable Invariant Sets
Naoya Takeishi, Yoshinobu Kawahara
Invariance and stability are essential notions in dynamical systems study, and thus it is of great interest to learn a dynamics model with a stable invariant set. However, existing…
An MCMC Method for Uncertainty Set Generation via Operator-Theoretic Metrics
Anand Srinivasan, Naoya Takeishi
Model uncertainty sets are required in many robust optimization problems, such as robust control and prediction with uncertainty, but there is no definite methodology to generate u…
A Characteristic Function for Shapley-Value-Based Attribution of Anomaly Scores
Naoya Takeishi, Yoshinobu Kawahara
In anomaly detection, the degree of irregularity is often summarized as a real-valued anomaly score. We address the problem of attributing such anomaly scores to input features for…
Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detection
Naoya Takeishi
We present a method to compute the Shapley values of reconstruction errors of principal component analysis (PCA), which is particularly useful in explaining the results of anomaly…
Physically-interpretable classification of biological network dynamics for complex collective motions
Keisuke Fujii, Naoya Takeishi, Motokazu Hojo +2
Understanding biological network dynamics is a fundamental issue in various scientific and engineering fields. Network theory is capable of revealing the relationship between eleme…
Knowledge-Based Regularization in Generative Modeling
Naoya Takeishi, Yoshinobu Kawahara
Prior domain knowledge can greatly help to learn generative models. However, it is often too costly to hard-code prior knowledge as a specific model architecture, so we often have…
Knowledge-Based Distant Regularization in Learning Probabilistic Models
Naoya Takeishi, Kosuke Akimoto
Exploiting the appropriate inductive bias based on the knowledge of data is essential for achieving good performance in statistical machine learning. In practice, however, the doma…
Dynamic and Static Topic Model for Analyzing Time-Series Document Collections
Rem Hida, Naoya Takeishi, Takehisa Yairi +1
For extracting meaningful topics from texts, their structures should be considered properly. In this paper, we aim to analyze structured time-series documents such as a collection…
Recent Developments in Aerial Robotics: A Survey and Prototypes Overview
Chun Fui Liew, Danielle DeLatte, Naoya Takeishi +1
In recent years, research and development in aerial robotics (i.e., unmanned aerial vehicles, UAVs) has been growing at an unprecedented speed, and there is a need to summarize the…
Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition
Naoya Takeishi, Yoshinobu Kawahara, Takehisa Yairi
Spectral decomposition of the Koopman operator is attracting attention as a tool for the analysis of nonlinear dynamical systems. Dynamic mode decomposition is a popular numerical…